OHDSI / OHDSI/FeatureExtraction
Add spline features for continuous variables
Nobody has claimed this yet.
- Dominant language
- R
- Stars
- 74
- Forks
- 63
- PR merge metrics
- No merged PRs in 30d
Description
Some of the non-binary variables such as age and Charlson index are currently provided as their verbatim value, which means models such as logistic regression (propensity scores) will model them as linear. However, a linear assumption is almost never realistic.
FeatureExtraction could also offer these same variables as splines, by already computing the spline design matrix. An example where I've done this before is here in the SelfControlledCaseSeries package. The hard part would be the administration of the covariate IDs for the design matrix variables.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the linked R/SccsDataConversion.R example around line 228, then trace how FeatureExtraction currently represents continuous covariates and assigns covariate IDs. Define how spline design-matrix variables should be exposed and identified; done means continuous variables can be offered as splines without ambiguous or conflicting covariate IDs.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- r
- Domain
- data
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100